submission_id: hastagaras-jamet-8b-l3-m_8788_v1
developer_uid: Hastagaras
status: inactive
model_repo: Hastagaras/Jamet-8B-L3-MK.V-BR4
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-06-07T01:06:30+00:00
model_name: b4
model_eval_status: success
model_group: Hastagaras/Jamet-8B-L3-M
num_battles: 15348
num_wins: 7966
celo_rating: 1195.64
safety_score: 0.96
propriety_score: 0.7010869565217391
propriety_total_count: 1104.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: b4
ineligible_reason: propriety_total_count < 5000
language_model: Hastagaras/Jamet-8B-L3-MK.V-BR4
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-06
win_ratio: 0.5190252801667969
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer
Waiting for job on hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer to finish
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ _____ __ __ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ /___/ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ Version: 0.8.14 ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ https://mk1.ai ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ The license key for the current software has been verified as ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ belonging to: ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ Chai Research Corp. ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ║ ║
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Downloaded to shared memory in 36.866s
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:02, 127.52it/s] Loading 0: 11%|█ | 31/291 [00:00<00:01, 150.06it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:01, 157.06it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 159.94it/s] Loading 0: 29%|██▊ | 83/291 [00:00<00:02, 84.61it/s] Loading 0: 33%|███▎ | 97/291 [00:00<00:02, 95.92it/s] Loading 0: 39%|███▉ | 113/291 [00:00<00:01, 108.34it/s] Loading 0: 45%|████▌ | 131/291 [00:01<00:01, 122.79it/s] Loading 0: 51%|█████ | 149/291 [00:01<00:01, 134.03it/s] Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 143.06it/s] Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 95.77it/s] Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 103.47it/s] Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 116.22it/s] Loading 0: 82%|████████▏ | 238/291 [00:02<00:00, 128.66it/s] Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 138.80it/s] Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 146.82it/s] Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.03it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: quantized model in 22.893s
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Processed model Hastagaras/Jamet-8B-L3-MK.V-BR4 in 62.336s
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8788-v1
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8788-v1/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8788-v1/config.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8788-v1/tokenizer.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8788-v1/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-jamet-8b-l3-m-8788-v1/flywheel_model.0.safetensors
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: warnings.warn(
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: return self.fget.__get__(instance, owner)()
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Saving duration: 0.397s
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.110s
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/config.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/special_tokens_map.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/tokenizer_config.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/merges.txt
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/vocab.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/tokenizer.json
hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-jamet-8b-l3-m-8788-v1_reward/reward.tensors
Job hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer completed after 185.25s with status: succeeded
Stopping job with name hastagaras-jamet-8b-l3-m-8788-v1-mkmlizer
Pipeline stage MKMLizer completed in 186.00s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-jamet-8b-l3-m-8788-v1
Waiting for inference service hastagaras-jamet-8b-l3-m-8788-v1 to be ready
Inference service hastagaras-jamet-8b-l3-m-8788-v1 ready after 30.207980155944824s
Pipeline stage ISVCDeployer completed in 36.24s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0060184001922607s
Received healthy response to inference request in 1.3619885444641113s
Received healthy response to inference request in 1.3069419860839844s
Received healthy response to inference request in 1.2871372699737549s
Received healthy response to inference request in 1.2204883098602295s
5 requests
0 failed requests
5th percentile: 1.2338181018829346
10th percentile: 1.2471478939056397
20th percentile: 1.2738074779510498
30th percentile: 1.2910982131958009
40th percentile: 1.2990200996398926
50th percentile: 1.3069419860839844
60th percentile: 1.3289606094360351
70th percentile: 1.3509792327880858
80th percentile: 1.4907945156097413
90th percentile: 1.748406457901001
95th percentile: 1.8772124290466308
99th percentile: 1.9802572059631347
mean time: 1.4365149021148682
Pipeline stage StressChecker completed in 7.82s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-jamet-8b-l3-m_8788_v1 status is now deployed due to DeploymentManager action
hastagaras-jamet-8b-l3-m_8788_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics